{"total":58,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32,"area":null},{"id":"2207.04806","title":"Repairing Neural Networks by Leaving the Right Past Behind","created":"2022-07-11","cited_by_count":27,"area":null},{"id":"2105.14203","title":"Understanding Instance-based Interpretability of Variational Auto-Encoders","created":"2021-05-29","cited_by_count":21,"area":null},{"id":"2205.11482","title":"Towards Tracing Factual Knowledge in Language Models Back to the Training Data","created":"2022-05-23","cited_by_count":21,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2205.00359","title":"Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees","created":"2022-04-30","cited_by_count":16,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2212.10722","title":"Contrastive Error Attribution for Finetuned Language Models","created":"2022-12-21","cited_by_count":12,"area":null},{"id":"2101.03841","title":"Model Generalization on COVID-19 Fake News Detection","created":"2021-01-11","cited_by_count":11,"area":null},{"id":"2101.08367","title":"Influence Estimation for Generative Adversarial Networks","created":"2021-01-20","cited_by_count":11,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2310.01765","title":"Data Cleaning and Machine Learning: A Systematic Literature Review","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2505.18976","title":"GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2102.06725","title":"Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2104.13794","title":"Finding High-Value Training Data Subset through Differentiable Convex Programming","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2311.16298","title":"Influence Scores at Scale for Efficient Language Data Sampling","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2412.03906","title":"Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2605.18814","title":"How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2103.13569","title":"Approximating Instance-Dependent Noise via Instance-Confidence Embedding","created":"2021-03-25","cited_by_count":3,"area":null},{"id":"2409.15126","title":"UTrace: Poisoning Forensics for Private Collaborative Learning","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2409.16978","title":"Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.12965","title":"Distributional Training Data Attribution: What do Influence Functions Sample?","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2508.14648","title":"Understanding Data Influence with Differential Approximation","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2508.20230","title":"Coresets from Trajectories: Selecting Data via Correlation of Loss Differences","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2510.11832","title":"Z0-Inf: Zeroth Order Approximation for Data Influence","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2601.21929","title":"LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2103.11807","title":"Data Cleansing for Deep Neural Networks with Storage-efficient Approximation of Influence Functions","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2506.00175","title":"Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.05281","title":"Fast-DataShapley: Neural Modeling for Training Data Valuation","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.21883","title":"GRASP-PsONet: Gradient-based Removal of Spurious Patterns for PsOriasis Severity Classification","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2306.00112","title":"Additional Positive Enables Better Representation Learning for Medical Images","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2402.08209","title":"Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2405.20531","title":"Mitigating the Impact of Labeling Errors on Training via Rockafellian Relaxation","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2407.16010","title":"AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2408.01365","title":"Data Debugging is NP-hard for Classifiers Trained with SGD","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2502.01669","title":"Delayed Feedback Modeling with Influence Functions","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2503.09721","title":"Finding the Muses: Identifying Coresets through Loss Trajectories","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2510.26185","title":"Accumulative SGD Influence Estimation for Data Attribution","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2604.03858","title":"A Bayesian Information-Theoretic Approach to Data Attribution","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2106.07217","title":"Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2502.10793","title":"Dynamic Influence Tracker: Measuring Time-Varying Sample Influence During Training","created":"2025-02-15","cited_by_count":0,"area":null},{"id":"2504.00603","title":"Data Cleansing for GANs","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2506.04047","title":"On Support Samples of Next Word Prediction","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.11584","title":"A Comparative Analysis of Influence Signals for Data Debugging","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2509.07319","title":"MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.12581","title":"Exploring Training Data Attribution under Limited Access Constraints","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2601.16651","title":"Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2607.16859","title":"Dataset Distillation by Influence Matching","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.22522","title":"From Detrimental to Beneficial: Dynamic Influence-based Valuation and Editing","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}